Combination of kernel PCA and linear support vector machine for modeling a nonlinear relationship between bioactivity and molecular descriptors

Fu, Guang‐Hui; Cao, Dong‐Sheng; Xu, Qingsong; Li, Hongdong; Liang, Yi‐Zeng

doi:10.1002/cem.1364

Cited by 19 publications

(10 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Support vector machine (SVM) was originally developed by Vapnik and coworkers and it has shown the promising capability for coping with a number of chemical classification problems [26][27][28][29][30][31][32]. SVM is based on the structure risk minimization principle from statistical learning theory.…”

Section: Support Vector Machinementioning

confidence: 99%

In silico toxicity prediction of chemicals from EPA toxicity database by kernel fusion-based support vector machines

Cao

Dong

Wang

et al. 2015

Chemometrics and Intelligent Laboratory Systems

Self Cite

View full text Add to dashboard Cite

Section: Support Vector Machinementioning

confidence: 99%

In silico toxicity prediction of chemicals from EPA toxicity database by kernel fusion-based support vector machines

Cao

Dong

Wang

et al. 2015

Chemometrics and Intelligent Laboratory Systems

Self Cite

View full text Add to dashboard Cite

“…However, several nonlinear QSAR methods have been proposed in recent years [32][33][34]. In QSAR methods based on regression analysis, it is necessary to previously assume an inputoutput relation (e.g.…”

Section: Artificial Neural Network (Anns)mentioning

confidence: 99%

Machine Learning Techniques and Drug Design

Gertrudes¹,

Maltarollo²,

Silva

et al. 2012

CMC

163

View full text Add to dashboard Cite

The interest in the application of machine learning techniques (MLT) as drug design tools is growing in the last decades. The reason for this is related to the fact that the drug design is very complex and requires the use of hybrid techniques. A brief review of some MLT such as self-organizing maps, multilayer perceptron, bayesian neural networks, counter-propagation neural network and support vector machines is described in this paper. A comparison between the performance of the described methods and some classical statistical methods (such as partial least squares and multiple linear regression) shows that MLT have significant advantages. Nowadays, the number of studies in medicinal chemistry that employ these techniques has considerably increased, in particular the use of support vector machines. The state of the art and the future trends of MLT applications encompass the use of these techniques to construct more reliable QSAR models. The models obtained from MLT can be used in virtual screening studies as well as filters to develop/discovery new chemicals. An important challenge in the drug design field is the prediction of pharmacokinetic and toxicity properties, which can avoid failures in the clinical phases. Therefore, this review provides a critical point of view on the main MLT and shows their potential ability as a valuable tool in drug design.

show abstract

“…Quantitative structure‐activity/property relationship (QSAR/QSPR), an important area in the chemical and biomedical sciences, searches the relationship between compounds and corresponding biological activities or chemical properties . In order to obtain this relationship, a variety of statistical learning methods have been proposed in QSAR/QSPR, including multiple linear regression (MLR), principal component regression, partial least square (PLS) regression , decision tree , support vector machines , random forest , boosting , and so on. In QSAR/QSPR studies, the chemical structure of compounds is represented by several descriptors, such as molecular constitutional, topological, shape, autocorrelation, and charge descriptors.…”

Section: Introductionmentioning

confidence: 99%

Incorporating PLS model information into particle swarm optimization for descriptor selection in QSAR/QSPR

Wang

Huang

Zhou

et al. 2015

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

As a representative paradigm of evolutionary algorithms, particle swarm optimization (PSO) has been combined with partial least square (PLS) (called PSO‐PLS) to select informative descriptors in quantitative structure‐activity/property relationship (QSAR/QSPR). However, one of the main limitations of PSO‐PLS is that it ignores PLS model information. In this paper, by incorporating the PLS model information into PSO‐PLS, we present a novel weighted sampling method (called WS‐PSO‐PLS) to choose the optimal descriptor subset. Due to the fact that the regression coefficients of the PLS model reflect the importance of descriptors in the model development, we firstly obtain the normalized regression coefficients by establishing the PLS model with all the descriptors. Afterward, weighted sampling is used to generate some individuals according to the aforementioned normalized regression coefficients. Finally, we employ some dimensions of the generated individuals to replace the corresponding dimensions of the individuals with poor quality in the population at each generation. WS‐PSO‐PLS has been assessed through three QSAR/QSPR datasets and the experimental results suggest that WS‐PSO‐PLS has the capability to effectively guide the search process by introducing the PLS model coefficients into PSO during the evolution and, therefore, performs better than PSO‐PLS. WS‐PSO‐PLS could be considered as a general and promising mechanism to introduce extra information to improve the performance of PSO for descriptor selection in QSAR/QSPR. Copyright © 2015 John Wiley & Sons, Ltd.

show abstract

Combination of kernel PCA and linear support vector machine for modeling a nonlinear relationship between bioactivity and molecular descriptors

Cited by 19 publications

References 33 publications

In silico toxicity prediction of chemicals from EPA toxicity database by kernel fusion-based support vector machines

In silico toxicity prediction of chemicals from EPA toxicity database by kernel fusion-based support vector machines

Machine Learning Techniques and Drug Design

Incorporating PLS model information into particle swarm optimization for descriptor selection in QSAR/QSPR

Contact Info

Product

Resources

About